HackerTrans
TopNewTrendsCommentsPastAskShowJobs

flux3125

no profile record

Submissions

The Dragon Hatchling: The Missing Link Between the Transformer and the Brain

arxiv.org
1 points·by flux3125·il y a 9 mois·0 comments

comments

flux3125
·il y a 21 jours·discuss
And now he's part of the confusing comment section lol
flux3125
·il y a 25 jours·discuss
Max 60 bucks a month. More than that and I'd just move to local qwen 35b or some other cheaper model on openrouter.
flux3125
·il y a 28 jours·discuss
This reminds me of Coconut Simulator
flux3125
·le mois dernier·discuss
Sorry, I forgot to add "on Linux" at the end. Still, that's a nice one!
flux3125
·le mois dernier·discuss
I'm curious if there's a program that uses a simple detection model for UX components to locate clickable areas. This would allow for global navigation similar to VimiumC
flux3125
·le mois dernier·discuss
It's called Time Series Forecasting
flux3125
·le mois dernier·discuss
They'll not only do it, but they'll also wrap it in a huge fat rounded border
flux3125
·il y a 2 mois·discuss
> It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked

Until it does. A simple curl request to a compromised website could inject a malicious prompt into it.
flux3125
·il y a 2 mois·discuss
> Don't listen to him

That's the idea
flux3125
·il y a 2 mois·discuss
You're absolutely right!
flux3125
·il y a 2 mois·discuss
At least it doesn't know my age

Oh wait
flux3125
·il y a 2 mois·discuss
[flagged]
flux3125
·il y a 3 mois·discuss
Point 2 is so true, I definitely find myself spending more time reading code vs writing it. LLMs can teach you a lot, but it's never the same as actually sitting down and doing it yourself.
flux3125
·il y a 3 mois·discuss
I was (positively) surprised that this didn't involve any AI.
flux3125
·il y a 3 mois·discuss
Code quality and IDEs aren't going anywhere, especially in complex enterprise systems. AI has improved a lot, but we're still far from a "forget about code" world.
flux3125
·il y a 3 mois·discuss
They are okay for vibe coding throw-away projects without spending your Anthrophic/OAI tokens
flux3125
·il y a 3 mois·discuss
You ARE the training data
flux3125
·il y a 3 mois·discuss
I stopped using Ollama a couple of months ago. Not out of frustration, but because llama.cpp has improved a lot recently with router mode, hot-swapping, a modern and simple web UI, MCP support and lots of other improvements.
flux3125
·il y a 3 mois·discuss
> so llama-swap can load

Just in case you haven't seen it yet, llama.cpp now has a router mode that lets you hot-swap models. I've switched over from llama-swap and have been happy with it.
flux3125
·il y a 3 mois·discuss
In my experience if you're coding or doing something that requires precision, quantizing the kv cache is definitely not worth it.

If you're just chatting or doing less precise things it's 1000% worth it going down to Q8 or sometimes even Q4